An Artificial Neural Network for Inferring Solar Wind Proxies at Mars

Abstract

We present a novel method to determine solar wind proxies from sheath measurements at Mars. Specifically, we develop an artificial neural network (ANN) to simultaneously infer seven solar wind proxies: ion density, ion speed, ion temperature, and interplanetary magnetic field magnitude and its vector components, using spacecraft measurements of ion moments, magnetic field magnitude, magnetic field components in the sheath, and the solar extreme ultraviolet flux. The ANN was trained and tested using 3 years of data from the Mars Atmosphere and Volatile EvolutioN (MAVEN) spacecraft. When compared with MAVEN spacecraft's in situ measured values of the solar wind parameters, we find that the ANN proxies for the solar wind ion density, ion speed, ion temperature, and interplanetary magnetic field magnitude have percentage differences of 50% or less for 84.4%, 99.9%, 86.8%, and 79.8% of the instances, respectively. For the cone angle and clock angle proxies, 69.1% and 53.3% of instances, respectively, have angle differences of 30∘ or less.